© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 646
    Prev
    Next
    INDEX
    Explanations

    references to laboratory tests and medical conditions involving immune response or blood incompatibility

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }\]
    -0.56
    ΗΣ
    -0.55
    #
    -0.55
    Obrázky
    -0.54
     (--
    -0.54
    nextDouble
    -0.52
    ronpa
    -0.51
    ждународ
    -0.50
    RTSC
    -0.49
    mazoo
    -0.49
    POSITIVE LOGITS
     positive
    4.34
     Positive
    4.00
    positive
    3.97
    Positive
    3.95
     POSITIVE
    3.66
    POSITIVE
    3.16
     negative
    3.11
     positiva
    2.98
     positif
    2.97
     positives
    2.95
    Activations Density 0.710%

    No Known Activations